Arxiv:1910.09700 4-bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Llama Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Pra-tham/quant_deepseekmath
Quant Deepseekmath Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Quant Deepseekmath Parameters and Internals
| LLM Name | Quant Deepseekmath |
| Repository 🤗 | https://huggingface.co/Pra-tham/quant_deepseekmath |
| Model Size | 4b |
| Required VRAM | 4.8 GB |
| Updated | 2025-06-09 |
| Maintainer | Pra-tham |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.39.3 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 102400 |
| Torch Data Type | bfloat16 |
Best Alternatives to Quant Deepseekmath
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Xgen Small 4B Instruct R | 256K / 17.7 GB | 49 | 2 |
| SJT 4B | 146K / 7.6 GB | 13 | 0 |
| ...lama 3.1 Nemotron Nano 4B V1.1 | 128K / 9 GB | 14124 | 88 |
| ...lama 3.1 Nemotron Nano 4B V1.1 | 128K / 9 GB | 626 | 4 |
| Basqui R1 4B V1 | 128K / 6.5 GB | 194 | 1 |
| Loxa 4B | 128K / 16 GB | 154 | 0 |
| CharGen V3 Mini | 128K / 9 GB | 50 | 6 |
| Nemotron W 4b MagLight 0.1 | 128K / 9.2 GB | 13 | 3 |
| Nemotron W 4b Halo 0.1 | 128K / 9.2 GB | 17 | 3 |
| Aura 4B | 128K / 9 GB | 10 | 11 |
Note: green Score (e.g. "73.2") means that the model is better than Pra-tham/quant_deepseekmath .
Rank the Quant Deepseekmath Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 48046 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124